lllyasviel / lllyasviel/FramePack
Future feature request - Something like ControlNet
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
I don't know if this is even possible with these models, but I would love to see better face control - more consistent with source images. Its good, but I would love to see better. Something like a ControlNet for faces. Support for pose videos like dense pose or the stick figure pose videos, or video 2 video for movement control, would be great. But completely understand if its outside of the scope of this project or this model's capabilities. Might be able to get more consistent faces if you have a reference face that you reference every few sections. That should help with drift as the video gets longer.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No files, tests, or entry points are named. First define whether face-reference conditioning, dense pose or stick-figure pose videos, and video-to-video movement control are in scope; done would require an agreed, testable feature specification.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100